Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Utvärdering av Amazon Machine Learning för taggsystem
KTH, School of Computer Science and Communication (CSC).
KTH, School of Computer Science and Communication (CSC).
2017 (Swedish)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Evaluation of Amazon Machine Learning for tag system (English)
Abstract [en]

How companies deal with machine learning is currently a highly-discussed topic, as it can facilitate corporate manual work by training computers to recognize patterns and thus automate the working procedure. However, this requires resources and knowledge in the field. As a result, various companies like Amazon and Google provide machine learning services without requiring the user to have deep knowledge in the area. This study evaluates Amazon Machine Learning program for a tag system with data from the media company Newstag. In order to make this evaluation, a larger amount of data with tags was obtained from the company. The result of the study indicates that Amazon's program do not work for multilabel classification.

Abstract [sv]

Hur företag ska hantera maskininlärning är i dagsläget ett mycket omtalat ämne då det kan underlätta företags manuella arbeten genom att träna upp datorer att känna igen mönster och på så sätt automatisera arbetsprocessen. Detta kräver dock resurser och kunskaper inom området. Som ett resultat av detta erbjuder olika företag som Amazon och Google maskininlärningstjänster utan att det krävs att användaren besitter djupa kunskaper inom området. I denna studie utvärderas Amazon Machine Learning programmet för ett taggsystem med data från medieföretaget Newstag. För att kunna göra denna utvärdering erhölls en större mängd data med taggar från företaget. Resultatet av studien pekar på att Amazons program inte fungerar för multilabel klassificering. 

Place, publisher, year, edition, pages
2017.
Keyword [sv]
amazon, maskininlärning, taggsystem
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-210792OAI: oai:DiVA.org:kth-210792DiVA, id: diva2:1120064
External cooperation
Newstag AB
Educational program
Master of Science in Engineering - Industrial Engineering and Management
Supervisors
Examiners
Available from: 2017-10-16 Created: 2017-07-05 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(1402 kB)36 downloads
File information
File name FULLTEXT01.pdfFile size 1402 kBChecksum SHA-512
c0697bd2e241773d04140a00bb9afd124d911b75834b9fcbe176b40b85c9c47f93fbc0a359c4774ca09ebb6fa35107bb2059c4f59b89dbb3b1748f7b0b954226
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 36 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 147 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
v. 2.34-SNAPSHOT
|